A method, device, equipment and storage medium for generating a certificate

Abstract

The present invention discloses a voucher generation method, device, equipment and storage medium. The voucher generation method includes: screening target voucher data in a historical voucher data set, and outputting the target voucher data to a sample data directory; based on the target voucher data in the sample data directory, building a data model with units, entries and vouchers as dimensions; in response to a user initiating a voucher generation instruction, generating a target voucher matching the generation elements in the voucher generation instruction based on the data model. The technical solution of the embodiment of the present invention can efficiently generate financial vouchers, and improve the efficiency and accuracy of voucher generation.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a credential generation method, device, equipment and storage medium. Background Art

[0002] Voucher entry is an important part of accounting work, which requires accurate entry of various financial transaction information into the accounting system based on the original documents.

[0003] Today, the generation of financial vouchers mainly relies on manual entry of each data indicator corresponding to the voucher into the system. The problem with manual entry of vouchers is that the voucher generation efficiency is low and the accuracy cannot be guaranteed. Therefore, how to quickly generate financial vouchers has become one of the issues that practitioners are concerned about. Summary of the invention

[0004] The present invention provides a voucher generation method, device, equipment and storage medium to achieve the effect of quickly generating financial vouchers.

[0005] According to one aspect of the present invention, there is provided a method for generating a credential, comprising:

[0006] Filtering target voucher data from the historical voucher data set, and outputting the target voucher data to a sample data directory;

[0007] Based on the target voucher data in the sample data directory, a data model is constructed with units, entries and vouchers as dimensions respectively;

[0008] In response to a user initiating a credential generation instruction, a target credential matching a generation element in the credential generation instruction is generated based on the data model.

[0009] According to another aspect of the present invention, there is provided a credential generation device, comprising:

[0010] A voucher data screening module, used to screen target voucher data in a historical voucher data set and output the target voucher data to a sample data directory;

[0011] A data model building module, used to build a data model based on the target voucher data in the sample data directory, with units, entries and vouchers as dimensions;

[0012] The credential generation module is used to generate a target credential matching the generation elements in the credential generation instruction based on the data model in response to a credential generation instruction initiated by a user.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the credential generation method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the credential generation method described in any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the credential generation method of any embodiment of the present disclosure is implemented.

[0019] The technical solution of the embodiment of the present invention filters target voucher data in a historical voucher data set, and outputs the target voucher data to a sample data directory, and then builds a data model based on the target voucher data in the sample data directory with units, entries and vouchers as dimensions, and finally responds to a user-initiated voucher generation instruction, generates a target voucher with generation elements in the voucher generation instruction based on the data model, which can realize rapid voucher generation and improve voucher generation efficiency and accuracy.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a flow chart of a method for generating a credential provided according to Embodiment 1 of the present invention;

[0023] Figure 2 is a flow chart of a method for generating a voucher according to Embodiment 2 of the present invention;

[0024] Figure 3 is a flow chart of a method for generating a credential provided according to Embodiment 3 of the present invention;

[0025] Figure 4 is a schematic diagram of the structure of a credential generating device provided according to a fourth embodiment of the present invention;

[0026] Figure 5 It is a schematic diagram of the structure of an electronic device for implementing the credential generation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] Figure 1 This is a flowchart of a voucher generation method provided in the first embodiment of the present invention. This embodiment is applicable to the case of generating financial vouchers according to a data model. The method can be executed by a voucher generation device. The voucher generation device can be implemented in the form of hardware and / or software. The voucher generation device can be configured in various general-purpose computing devices. Figure 1 As shown, the method includes:

[0031] S110. Filter target voucher data in the historical voucher data set, and output the target voucher data to the sample data directory.

[0032] The historical voucher data set contains historical voucher data within a set historical period, for example, historical voucher data within 5 years. Each historical voucher data includes the unit to which the voucher belongs, the city or province, the voucher time, and at least one entry. Each entry includes the summary, account, and amount of the entry. The amount can include the debit amount and the credit amount.

[0033] In the embodiment of the present invention, in order to realize the rapid generation of vouchers, it is necessary to build a data model based on historical voucher data. Since the historical voucher data set contains all historical voucher data in the historical time period, some low-frequency historical voucher data may be included. For example, in the past five years, this historical voucher data has only appeared once. If the data model is generated based on all historical voucher data, the model will contain low-frequency historical voucher data, which has a very low usage frequency, and the model will be bulky, which increases the data retrieval workload when using the data model to generate vouchers.

[0034] Therefore, it is necessary to remove some historical voucher data with low usage frequency from the historical voucher data set, and output the remaining historical voucher data as target voucher data to the sample data directory, for example, output the filtered target voucher data to the NG-DATA directory.

[0035] In a specific example, one or more preset indicators, such as summary, subject, and amount, are extracted from the historical voucher data, and then a feature vector of the historical voucher data is generated based on the indicators. Based on the feature vector, the historical voucher data are compared in pairs, and those with a similarity greater than 0.8 are determined to be the same historical voucher data. Finally, the historical voucher data with a number of occurrences less than the set threshold is deleted, and the remaining historical voucher data is output to the NG-DATA directory as the target voucher data.

[0036] In another specific example, one or more preset indicators, such as summary, subject and amount, are extracted from the historical voucher data, and then a feature vector of the historical voucher data is generated based on the indicators. The year with the most historical voucher data records is used as the control year, and the historical voucher data recorded in the control year is used as the control voucher data. Each piece of historical voucher data is compared with the control voucher data in the control year one by one. If there is a control voucher data with a similarity greater than a set threshold, for example, 0.8 with the historical voucher data, the current historical voucher data is output as the target voucher data to the sample data directory; if there is no control voucher data with a similarity greater than the set threshold with the historical voucher data, the next piece of historical voucher data is taken for comparison.

[0037] By screening the target voucher data that meets the needs of model building in the historical voucher data set, the size of the data model can be reduced, and in the subsequent process of generating vouchers based on the data model, the data retrieval workload can be reduced and the data retrieval efficiency can be improved.

[0038] S120. Based on the target voucher data in the sample data directory, a data model is constructed with unit, entry and voucher as dimensions.

[0039] The data model is generated based on the target voucher data and contains a wide table of multiple target voucher data. Exemplarily, the data model can be a unit data model built with the unit as the dimension, an entry data model built with the entry as the dimension, or a voucher data model built with the voucher as the dimension.

[0040] In an embodiment of the present invention, in order to meet the needs of users to query voucher data from different dimensions when generating financial vouchers, based on the target voucher data in the sample data directory, data models are constructed with units, entries and vouchers as dimensions to obtain unit data models, entry data models and voucher data models.

[0041] When you need to query voucher data by unit or voucher time, you can query data in the unit data model; when you need to query voucher data by keyword, you can use the entry data model and voucher data model together to query data.

[0042] S130. In response to a user-initiated credential generation instruction, a target credential with generation elements in the credential generation instruction is generated based on a data model.

[0043] The voucher generation instruction is initiated by a user who needs to generate a financial voucher, which contains the generation elements required to generate the voucher, such as the voucher generation cycle or voucher keywords.

[0044] In the embodiment of the present invention, after receiving the credential generation instruction initiated by the user, the generation elements contained in the credential generation instruction are first read, and the corresponding target credential data is extracted from the data model based on the generation elements. Finally, the target credential is generated based on the extracted target credential data.

[0045] In a specific example, in the user-initiated credential generation instruction, the generated element extracted is the credential generation period, then based on the current time and the credential generation period, the credential data is extracted from the unit data model, and a periodic credential data list is generated. Further, according to the target period selected by the user, the credential data corresponding to the target period is extracted from the periodic credential list, and the target credential is generated based on the extracted credential data.

[0046] In another specific example, when the user initiates a voucher generation instruction and the generated element is a keyword, the target voucher data with the highest correlation with the keyword is first obtained in the voucher model and filled in. Further, based on the keyword and the subject information in the target voucher data with the highest correlation, the voucher data is loaded in the entry model, and finally the target voucher is generated based on the loaded voucher data.

[0047] The technical solution of the embodiment of the present invention filters target voucher data in a historical voucher data set, and outputs the target voucher data to a sample data directory, and then builds a data model based on the target voucher data in the sample data directory with units, entries and vouchers as dimensions, and finally responds to a user-initiated voucher generation instruction, generates a target voucher with generation elements in the voucher generation instruction based on the data model, which can realize rapid voucher generation and improve voucher generation efficiency and accuracy.

[0048] Embodiment 2

[0049] Figure 2 This is a flowchart of a credential generation method provided in the second embodiment of the present invention. This embodiment further refines the above embodiment and provides specific steps of screening target credential data from a historical credential data set and outputting the target credential data to a sample data directory, as well as specific steps of generating a target credential with the generation element in the credential generation instruction based on a data model in response to a user-initiated credential generation instruction. Figure 2 As shown, the method includes:

[0050] S210: extracting historical voucher data from a historical voucher data set, and generating a feature vector of the historical voucher data based on preset data indicators.

[0051] In an embodiment of the present invention, historical voucher data is sequentially extracted from a historical voucher data set, and a feature vector of the historical voucher data is generated based on a pre-set data index. For example, a feature vector of the historical voucher data can be generated based on a summary, a subject, a credit amount, and a debit amount.

[0052] S220. Calculate the similarity between the feature vector of the historical voucher data and the feature vector of the comparison voucher data.

[0053] In the embodiment of the present invention, in order to filter out the historical voucher data with a high usage frequency, the similarity between the feature vector of the historical voucher data and the feature vectors of a plurality of reference voucher data can be calculated. The reference voucher data can be all the historical voucher data contained in the year with the most historical voucher data, or the historical voucher data in the reference voucher data set established according to actual usage requirements.

[0054] S230. When the similarity is greater than a set threshold, the historical voucher data is output as target voucher data to the sample data directory.

[0055] In the embodiment of the present invention, the similarity between the feature vector of the historical voucher data and the feature vector of each comparison voucher data is calculated. If there is comparison voucher data whose similarity with the historical voucher data is greater than a set threshold, the current historical voucher data is output to the sample data directory.

[0056] S240. Based on the target voucher data in the sample data directory, a unit data model is constructed with the unit as the dimension.

[0057] In an embodiment of the present invention, in order to meet the multi-dimensional voucher data retrieval requirements, a unit data model is constructed based on the target voucher data in the sample data directory and with the unit as the dimension. Specifically, for each piece of historical voucher data, the specified index data is first extracted. For example, the specified data may be entry data, specifically including entry summary, account and amount. It is determined whether the data identical to the above index data already exists in the currently unfinished unit data model (hereinafter referred to as the unit transition model). If there is a piece of data identical to the above entry summary, account and amount, it is not inserted. If not, the entry summary, account and amount of the data are inserted into the first node in the unit transition model. Further, the target time in the target voucher data is extracted, and it is determined whether the target time already exists in the unit transition model. If it exists, the existing target time is directly associated with the entry data in the first node; if not, the target time is inserted into the second node in the unit transition model, and the target time is associated with the entry data in the first node. Further, the target unit of the target voucher data is obtained, and it is determined whether the target unit already exists in the unit transition model. If so, the existing target unit is directly associated with the target time in the second node; if not, the target unit is inserted into the third node in the unit transition model, and the target unit is associated with the target time in the second node. After completing the insertion process of all historical voucher data, the obtained unit transition model is the final unit data model.

[0058] Optionally, based on the target voucher data in the sample data directory, a unit data model is constructed with the unit as the dimension, including:

[0059] Traverse the target credential data in the sample data directory and obtain the unit cyclic redundancy check CRC code corresponding to the target credential data;

[0060] Based on the unit CRC encoding, the target voucher data is grouped, and the target voucher data is transferred to the corresponding data queue according to the grouping;

[0061] Start the model building task corresponding to each data queue in parallel, and insert the target voucher data in the data queue into the unit transition model according to the pre-set element insertion order;

[0062] After the target voucher data in all data queues are inserted into the unit transition model, the unit transition model is determined as the unit data model.

[0063] In this optional embodiment, a specific method for constructing a unit data model based on the target voucher data in the sample data directory and taking the unit as the dimension is provided: first, the target voucher data in the sample data directory is traversed to obtain all the units under the sample data directory, and then the unit cyclic redundancy check (CRC) code corresponding to the target voucher data is obtained according to the unit. Further, the code is modulo, for example, 100 modulo. According to the modulo result, a data channel with a corresponding sequence number is established. For example, by taking a modulo of 100, a maximum of 100 modulo results can be obtained, that is, a maximum of 100 data channels are established. The target voucher data is selected according to the corresponding modulo result, and the corresponding digital data channel is passed into the corresponding Redis data queue. This method will input the target voucher data of the same unit into the same data queue. Further, the model construction task corresponding to each data queue is started in parallel, and the target voucher data in the data queue is inserted into the unit transition model according to the pre-set element insertion order. It is worth noting that during the data insertion process, it will first verify whether the data exists in the unit transition model. If it exists, it will not be inserted repeatedly. Therefore, when each task inserts data into the unit transition model, it is necessary to apply for a Redis lock to ensure that other tasks wait and avoid duplicate data entry. Finally, after inserting the target voucher data in all data queues into the unit transition model, the unit transition model is determined as the unit data model.

[0064] Optionally, inserting the target voucher data in the data queue into the unit transition model according to a preset element insertion order includes:

[0065] Extract target voucher data from the data queue in sequence, obtain target indicator data in the target voucher data, and insert the target indicator data into the unit transition model if the existing indicator data of the unit transition model does not contain the target indicator data; the target indicator data includes entry summary, account and amount;

[0066] Extracting the target time in the target voucher data, inserting the target time into the unit transition model if the target time is not included in the existing time in the unit transition model, and associating the target time with the target indicator data;

[0067] The target unit in the target voucher data is obtained. If the target unit is not included in the existing units in the unit transition model, the target unit is inserted into the unit transition model, and the target unit is associated with the target time.

[0068] In this optional embodiment, a specific method is provided for inserting the target voucher data in the data queue into the unit transition model according to a preset element insertion order: first, extract the target voucher data from the data queue in sequence, and obtain the target indicator data in the target voucher data, for example, the target indicator data obtained is the entry summary, subject and amount. Then, it is determined whether there is a piece of data in the unit transition model, which is the same as the entry summary, subject and amount extracted from the current target voucher data. If the target indicator data is not included in the existing indicator data of the unit transition model, the target indicator data is inserted into the unit transition model.

[0069] Further, the target time in the target voucher data is extracted. If the target time is not included in the existing time in the unit transition model, the target time is inserted into the unit transition model, and the target time is associated with the target indicator data. Finally, the target unit in the target voucher data is obtained. If the target unit is not included in the existing unit in the unit transition model, the target unit is inserted into the unit transition model, and the target unit is associated with the target time. After completing the insertion of all target voucher data in the sample data directory, the meshed unit data model is obtained as shown in Table 1.

[0070] Table 1

[0071]

[0072] It is worth noting that in the meshed unit data model, since there may be gaps between different time units, it is necessary to check the time for duplication to reduce data node duplication. For example, Wednesday, May 28, 2024, will be constructed as: W: Wednesday, M: May 26 / 27 / 28 / 29 / 30, Y: May 28 plus or minus 10 days. Multiple times within this range can be merged.

[0073] In addition, since there may be differences between different units of entry summary nodes, vector extraction will be performed on the entry summaries in a unified manner, and all entry summaries at the same time will be compared using the K-neighbor algorithm. Those with a similarity greater than 0.8 will be judged as identical by default, and the entry summaries will be merged.

[0074] S250: In response to a credential generation instruction initiated by a user, obtain a credential generation cycle in the credential generation instruction.

[0075] In the embodiment of the present invention, after receiving the credential generation instruction initiated by the user, the credential generation cycle in the credential generation instruction is first obtained. The credential generation cycle is used to limit the span of the credential data covered by the credential to be generated. For example, if the credential generation cycle is 1 year, it means that the credential to be generated covers 1 year of credential data.

[0076] S260. Obtain system time, extract voucher data from the unit data model according to the system time and the voucher generation cycle, and generate a periodic voucher data list.

[0077] In the embodiment of the present invention, after the user logs in to the system, the current system time is obtained through the time() function, and the voucher data is extracted from the unit data model according to the system time and the voucher generation cycle, and a periodic voucher data list is generated. For example, the voucher generation cycle is weekly, monthly or annual.

[0078] In a specific example, after obtaining the system time, a time axis is constructed based on the system time and the voucher generation cycle. For example, the system time is used as the end point of the time, and the voucher generation cycle is used as the time length, and multiple cycles are calculated forward in sequence. A periodic voucher data list is generated based on the target voucher data included in each cycle.

[0079] S270. According to the target period selected by the user, the target period data corresponding to the target period is extracted from the periodic voucher list, and the target voucher is generated according to the target period data.

[0080] In an embodiment of the present invention, after a periodic voucher data list is generated, the user is prompted to select a target period, and then based on the target period selected by the user, the target period data corresponding to the target period is extracted from the periodic voucher list, and the target voucher is generated based on the target period data.

[0081] In a specific example, the voucher generation cycle is monthly, and the system time is May 28, 2024. Then, the cycles to be selected can be determined in sequence to include: April 28, 2024 - May 28, 2024, March 28, 2024 - April 28, 2024, and February 28, 2024 - March 28, 2024, ... According to the above cycles to be selected, the target voucher data corresponding to the cycle is obtained in sequence, and a periodic voucher data list is generated. Finally, according to the target cycle selected by the user, for example, February 28, 2024 - March 28, 2024, the corresponding target voucher data is obtained according to the target cycle, and finally the target voucher is generated according to the target voucher data.

[0082] The technical solution of the embodiment of the present invention can reduce the volume of the unit data model and improve the data retrieval efficiency in the voucher generation process by comparing the historical voucher data in the historical voucher data set with the control voucher data, and screening out the data with higher usage frequency as the target voucher data output, and can subsequently generate vouchers periodically based on the unit voucher data to improve the voucher generation efficiency.

[0083] Embodiment 3

[0084] Figure 3 This is a flowchart of a credential generation method provided in Embodiment 3 of the present invention. This embodiment further refines the above embodiments and provides specific steps for generating a target credential with the generation elements in the credential generation instruction based on a data model in response to a user initiating a credential generation instruction. Figure 3 As shown, the method includes:

[0085] S310. Filter target voucher data in the historical voucher data set, and output the target voucher data to the sample data directory.

[0086] S320. Based on the target voucher data in the sample data directory, an entry data model is constructed with entry as the dimension.

[0087] In an embodiment of the present invention, in order to meet the multi-dimensional voucher data retrieval requirements, an entry data model is constructed based on the target voucher data in the sample data directory and with entries as the dimension. Specifically, for each target voucher data, at least one entry contained therein is sequentially extracted as the target entry, and the entry feature vector is calculated based on the entry summary, subject, and amount of the target entry. The entry feature vector is further compared with the entry feature vector of the existing entry in the current entry data model (hereinafter referred to as the entry transition model). If there is no existing entry with a similarity greater than a threshold, the target entry in the current target voucher data is directly inserted into the entry transition model, and the voucher, affiliated unit / city are also correspondingly inserted into the entry transition model.

[0088] If there is a first existing entry with a similarity higher than the set threshold with the target entry, the first voucher to which the first existing entry belongs is determined in the entry transition model, and each existing entry in the first voucher is compared with each entry to be entered in the target voucher data. When the proportion of entries to be entered with a similarity higher than the set threshold in all entries to be entered in the target voucher data reaches a set ratio, the target voucher data and the first voucher are merged. Finally, after the target voucher data in the sample data directory is traversed, the entry transition model obtained is used as the entry data model.

[0089] Optionally, based on the target voucher data in the sample data directory, build an entry data model with entry as the dimension, including:

[0090] Extract target voucher data from the sample data directory, and sequentially obtain the entries to be entered in the target voucher data as target entries;

[0091] Compare the target entry with the existing entries in the entry transition model. If there is no existing entry with a similarity with the target entry higher than the set threshold, insert the target voucher data into the entry transition model.

[0092] If there is a first existing entry whose similarity with the target entry is higher than the set threshold, the first voucher to which the first existing entry belongs is determined in the entry transition model;

[0093] Compare each existing entry in the first voucher with each entry to be entered in the target voucher data, and merge the target voucher data with the first voucher when the entries to be entered with a similarity greater than a set threshold account for a set proportion of all the entries to be entered in the target voucher data;

[0094] After traversing the target voucher data in the sample data directory, the entry transition model obtained is used as the entry data model.

[0095] In this optional embodiment, a specific method for constructing an entry data model based on the target voucher data in the sample data directory and taking entries as the dimension is provided: first, the target voucher data is extracted from the sample data directory, and the entries to be entered in the target voucher data are obtained in sequence as the target entries. Then, the target entry is compared with the existing entries in the entry transition model. If there is no existing entry with a similarity with the target entry higher than a set threshold, the target voucher data is inserted into the entry transition model. It can be seen that the summary, subject and amount of the target entry are obtained to generate a feature vector of the target entry, and the similarity with the existing entry is calculated based on the feature vector.

[0096] If there is no existing entry with a similarity with the target entry higher than the set threshold, the entry to be entered, the voucher to which the target entry belongs, and the unit / city / province to which the target entry belongs are correspondingly inserted into the entry transition model.

[0097] If there is a first existing entry with a similarity higher than the set threshold with the target entry, it indicates that the current target voucher data may have been entered. To avoid duplicate entry of vouchers, the first voucher to which the first existing entry belongs is determined in the entry transition model, and each existing entry in the first voucher is compared with each entry to be entered in the target voucher data. When the proportion of entries to be entered with a similarity higher than the set threshold in all entries to be entered in the target voucher data reaches a set ratio, the target voucher data and the first voucher are merged. After traversing the target voucher data in the sample data directory, the entry transition model obtained as the entry data model is shown in Table 2, which contains the model relationships at the unit level, prefecture level, and provincial level.

[0098] Table 2

[0099]

[0100] S330. Based on the target voucher data in the sample data directory, a voucher data model is constructed with the voucher as the dimension.

[0101] In the embodiment of the present invention, in order to meet the multi-dimensional voucher data retrieval requirements, a voucher data model is constructed based on the target voucher data in the sample data directory and with the voucher as the dimension. Specifically, the target voucher data is first extracted from the sample directory, and the voucher summary therein is segmented. Further, based on the words obtained by the segmentation, the voucher data is extracted from the target voucher data with the unit, city and province as the dimensions. The final dimensions, segmentation results and extracted voucher data are used to construct the voucher data model as shown in Table 3.

[0102] Table 3

[0103]

[0104] Optionally, based on the target voucher data in the sample data directory, a voucher data model is constructed with vouchers as the dimension, including:

[0105] Extract target voucher data from the sample data directory, and segment the voucher summary in the target voucher data;

[0106] Based on the word segmentation results, extract voucher data from the target voucher data using units, cities and provinces as dimensions;

[0107] Build a voucher data model based on dimensions, word segmentation results and extracted voucher data.

[0108] S340: In response to the user initiating a credential generation instruction, obtain a credential keyword in the credential generation instruction.

[0109] In the embodiment of the present invention, after receiving the voucher generation instruction initiated by the user, the generation element in the configuration generation instruction is obtained to be the voucher keyword, so as to perform subsequent target voucher data screening according to the keyword. For example, the user enters "Dragon Boat Festival activities" and obtains the keyword "activity".

[0110] S350. Perform keyword matching in the voucher data model to obtain first voucher data that matches the voucher keyword, and fill the first voucher data into the initial voucher to obtain a transitional voucher.

[0111] In an embodiment of the present invention, after obtaining the keyword, keyword matching is performed in the voucher data model to obtain the first voucher data matching the voucher keyword. Then the first voucher data is filled into the initial voucher to obtain the transition voucher. Among them, the specific method of performing keyword matching in the voucher data model to obtain the first voucher data matching the voucher keyword can be: taking the unit, city and province as dimensions, respectively, to obtain the keywords of the entries contained in the target voucher data in the voucher data model. Then, small top heaps with units, cities and provinces as dimensions are established respectively, and the length of each small top heap is half of the total number of subjects in the current dimension. Then the keyword input by the user is matched with the keyword of the entry in each dimension. If the match is successful (for example, the keyword of the entry with a similarity greater than 0.8 is matched), the number of occurrences of the subject information of the successfully matched keyword is obtained, and the number of occurrences is compared with the top node of the heap. If the number is smaller than the top of the heap, it is discarded, otherwise the top of the heap is replaced and the small top heap is adjusted until all lists of keyword matches are traversed, and the top of the small top heap is taken out. Among them, the top priorities of the small top piles of the unit, prefecture-level city and province dimensions are from high to low: unit, prefecture-level city and province. That is, if the most matching keywords are found in the three small top piles, the first voucher data associated with the top of the small top pile of the unit dimension in the voucher data model is preferentially used. The first voucher data is filled into the initial blank voucher to obtain a transition voucher.

[0112] S360. According to the voucher keyword and the subject to which the target voucher data belongs, the second voucher data is obtained in the entry data model, and the transition voucher is completed with the second voucher data to obtain the target voucher.

[0113] In the embodiment of the present invention, since the voucher model may not store all historical voucher data, further, the current system time is extracted, the timeline is constructed, and a periodic voucher data list is obtained. According to the voucher keyword and the subject to which the target voucher data belongs, as well as the selected target period, the second voucher data is obtained in the entry data model, and the transition voucher is completed using the second voucher data. Specifically, if one item is obtained, the complete voucher data is directly completed; if there are multiple items of loaded data, a logistic regression algorithm is further used to predict and complete the data according to the user-input keywords and auxiliary items to obtain the target voucher.

[0114] Optionally, in response to a user initiating a credential generation instruction, generating a target credential matching a generation element in the credential generation instruction based on the data model further includes:

[0115] When no voucher keyword is matched in the voucher data model, the entry summary, subject and amount of each entry are sequentially extracted from the entry data model, and an entry feature vector is generated based on the entry summary, subject and amount;

[0116] The feature vector of the voucher keyword is compared with the entry feature vector. When the similarity is higher than a set threshold, a target voucher is constructed based on the target voucher data associated with the entry feature vector.

[0117] In the embodiment of the present invention, there is also a situation that when the voucher keyword is not matched in the voucher data model, the entry summary, subject and amount of each entry are sequentially extracted in the entry data model, and the entry feature vector is generated based on the entry summary, subject and amount. Further, the feature vector of the voucher keyword and the entry feature vector are compared, and when the similarity is higher than the set threshold, the target voucher is constructed based on the target voucher data associated with the entry feature vector.

[0118] Optionally, the target voucher can also be generated in a question-and-answer format. After the user inputs the relevant information by voice, the input information is segmented. For example, if the user initiates the voice "generate a withdrawal voucher for me", the words are segmented and the keywords include "generate", "one", "withdraw" and "voucher". Based on this information, the voucher with the operation to be performed as "generate", the quantity as "one", and the summary as "withdraw" can be defined. The subsequent process of generating the voucher is the same as the process of generating the target voucher based on the voucher keywords mentioned above, so it will not be repeated here.

[0119] Of course, if historical credential data associated with the user who currently initiates the instruction is stored, the historical credential data of the user will be used first to generate the target credential; if there is no historical credential data associated with the current user, the historical credential data of other users on the same node can be further obtained, and the target credential can be generated based on the historical credential data of other users at the same stage; if neither of the above two items exists, the credential data model and the entry data model are used to generate the target credential, so that the generated target credential can be as close to the user's needs as possible.

[0120] According to the technical solution of the embodiment of the present invention, after establishing data models in the entry dimension and the voucher dimension respectively, the user only needs to type or input keywords by voice to generate target entries matching the keywords according to the data model. There is no need for the user to manually input voucher data, which simplifies the voucher generation process and improves the configuration generation efficiency and accuracy.

[0121] Embodiment 4

[0122] Figure 4 This is a schematic diagram of the structure of a credential generation device provided in Embodiment 4 of the present invention. Figure 4 As shown, the device comprises:

[0123] The voucher data screening module 410 is used to screen the target voucher data in the historical voucher data set and output the target voucher data to the sample data directory;

[0124] A data model building module 420 is used to build a data model based on the target voucher data in the sample data directory, with units, entries and vouchers as dimensions;

[0125] The credential generation module 430 is used to generate a target credential matching the generation elements in the credential generation instruction based on the data model in response to a credential generation instruction initiated by the user.

[0126] The technical solution of the embodiment of the present invention filters target voucher data in a historical voucher data set, and outputs the target voucher data to a sample data directory, and then builds a data model based on the target voucher data in the sample data directory with units, entries and vouchers as dimensions, and finally responds to a user-initiated voucher generation instruction, generates a target voucher with generation elements in the voucher generation instruction based on the data model, which can realize rapid voucher generation and improve voucher generation efficiency and accuracy.

[0127] Optionally, the credential data screening module 410 is specifically used to:

[0128] Extracting historical voucher data from a historical voucher data set, and generating a feature vector of the historical voucher data based on a preset data indicator;

[0129] Calculating the similarity between the feature vector of the historical voucher data and the feature vector of the comparison voucher data;

[0130] When the similarity is greater than a set threshold, the historical credential data is output as target credential data to the sample data directory.

[0131] Optionally, the data model building module 420 includes:

[0132] A code acquisition unit, used to traverse the target credential data in the sample data directory and acquire a unit cyclic redundancy check CRC code corresponding to the target credential data;

[0133] A data grouping unit, used for grouping the target voucher data based on the unit CRC encoding, and transferring the target voucher data into the corresponding data queue according to the grouping;

[0134] The data insertion unit is used to start the model building task corresponding to each data queue in parallel, and insert the target voucher data in the data queue into the unit transition model according to the pre-set element insertion order;

[0135] The unit data model construction unit is used to determine the unit transition model as the unit data model after inserting the target credential data in all data queues into the unit transition model.

[0136] Optionally, a data insertion unit is specifically used to:

[0137] Extracting target voucher data from the data queue in sequence, obtaining target indicator data in the target voucher data, and inserting the target indicator data into the unit transition model when the target indicator data is not included in the existing indicator data of the unit transition model; the target indicator data includes an entry summary, a subject, and an amount;

[0138] Extracting the target time in the target voucher data, inserting the target time into the unit transition model if the target time is not included in the existing time in the unit transition model, and associating the target time with the target indicator data;

[0139] The target unit in the target voucher data is obtained, and if the target unit is not included in the existing units in the unit transition model, the target unit is inserted into the unit transition model, and the target unit is associated with the target time.

[0140] Optionally, the data model building module 420 includes:

[0141] A target entry acquisition unit is used to extract target voucher data from the sample data directory, and sequentially acquire the entries to be entered in the target voucher data as target entries;

[0142] An entry comparison unit is used to compare the target entry with the existing entries in the entry transition model, and if there is no existing entry with a similarity with the target entry higher than a set threshold, insert the target voucher data into the entry transition model;

[0143] a voucher determination unit, configured to determine, in the entry transition model, a first voucher to which the first existing entry belongs if there is a first existing entry whose similarity to the target entry is higher than a set threshold;

[0144] a voucher merging unit, configured to compare each existing entry in the first voucher with each entry to be entered in the target voucher data, and merge the target voucher data with the first voucher when the entries to be entered with a similarity greater than a set threshold account for a set proportion of all the entries to be entered in the target voucher data;

[0145] The entry data model building unit is used to use the entry transition model obtained after traversing the target voucher data in the sample data directory as the entry data model.

[0146] Optionally, the data model building module 420 includes:

[0147] A summary word segmentation unit is used to extract target voucher data from the sample data directory and perform word segmentation on the voucher summary in the target voucher data;

[0148] A voucher data extraction unit is used to extract voucher data from target voucher data based on word segmentation results and taking units, cities and provinces as dimensions;

[0149] The voucher data model building unit is used to build a voucher data model based on dimensions, word segmentation results and extracted voucher data.

[0150] Optionally, the credential generation module 430 includes:

[0151] A cycle acquisition unit, configured to acquire a credential generation cycle in the credential generation instruction in response to a credential generation instruction initiated by a user;

[0152] a voucher data list generating unit, configured to obtain system time, extract voucher data from the unit data model according to the system time and the voucher generation period, and generate a periodic voucher data list;

[0153] The first credential generating unit is used to extract target period data corresponding to the target period from the periodic credential list according to the target period selected by the user, and generate a target credential according to the target period data.

[0154] Optionally, the credential generation module 430 further includes:

[0155] A keyword acquisition unit, configured to acquire a credential keyword in the credential generation instruction in response to a credential generation instruction initiated by a user;

[0156] A keyword matching unit, configured to perform keyword matching in the credential data model, obtain first credential data matching the credential keyword, and fill the first credential data into an initial credential to obtain a transitional credential;

[0157] The second voucher generating unit is used to obtain the second voucher data in the entry data model according to the voucher keyword and the subject to which the target voucher data belongs, and use the second voucher data to complete the transition voucher to obtain the target voucher.

[0158] Optionally, the credential generation module 430 further includes:

[0159] An entry feature vector generating unit, configured to extract the entry summary, subject and amount of each entry in the entry data model in sequence when the voucher keyword is not matched in the voucher data model, and generate an entry feature vector based on the entry summary, subject and amount;

[0160] The third voucher generation unit compares the feature vector of the voucher keyword with the entry feature vector, and constructs a target voucher based on the target voucher data associated with the entry feature vector when the similarity is higher than a set threshold.

[0161] The credential generation device provided in the embodiment of the present invention can execute the credential generation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0162] In the technical solution of the present invention, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0163] Embodiment 5

[0164] According to an embodiment of the present invention, the present invention also provides an electronic device, a readable storage medium and a computer program product.

[0165] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, applicators, blade applicators, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0166] like Figure 5As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0167] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0168] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a credential generation method.

[0169] In some embodiments, the credential generation method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the credential generation method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the credential generation method in any other appropriate manner (e.g., by means of firmware).

[0170] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0171] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or application.

[0172] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0173] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0174] The systems and techniques described herein may be implemented in a computing system that includes a backend component (e.g., as a data applier), or a computing system that includes a middleware component (e.g., an application applier), or a computing system that includes a frontend component (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0175] A computing system may include a client and an application server. The client and the application server are generally remote from each other and usually interact through a communication network. The relationship between the client and the application server is generated by computer programs running on corresponding computers and having a client-application server relationship with each other. The application server may be a cloud application server, also known as a cloud computing application server or a cloud host, which is a host product in a cloud computing application system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS applications.

[0176] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0177] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for generating a voucher, characterized in that: include: Filtering target voucher data from the historical voucher data set, and outputting the target voucher data to a sample data directory; Based on the target voucher data in the sample data directory, a data model is constructed with units, entries and vouchers as dimensions respectively; In response to a user initiating a credential generation instruction, generating a target credential matching a generation element in the credential generation instruction based on the data model; Wherein, based on the target voucher data in the sample data directory, a unit data model is constructed with the unit as the dimension, including: Traverse the target credential data in the sample data directory to obtain a unit cyclic redundancy check CRC code corresponding to the target credential data; Based on the unit CRC encoding, the target voucher data is grouped, and the target voucher data is transferred to the corresponding data queue according to the grouping; Start the model building task corresponding to each data queue in parallel, and insert the target voucher data in the data queue into the unit transition model according to the pre-set element insertion order; After inserting the target voucher data in all data queues into the unit transition model, determining the unit transition model as a unit data model; Based on the target voucher data in the sample data directory, an entry data model is constructed with entries as the dimension, including: Extracting target voucher data from the sample data directory, and sequentially obtaining the entries to be entered in the target voucher data as target entries; Compare the target entry with the existing entries in the entry transition model, and if there is no existing entry with a similarity with the target entry higher than a set threshold, insert the target voucher data into the entry transition model; If there is a first existing entry whose similarity with the target entry is higher than a set threshold, determining a first voucher to which the first existing entry belongs in the entry transition model; Compare each existing entry in the first voucher with each entry to be entered in the target voucher data, and merge the target voucher data and the first voucher when the entries to be entered with a similarity greater than a set threshold account for a set proportion of all the entries to be entered in the target voucher data; After traversing the target voucher data in the sample data directory, the entry transition model obtained is used as the entry data model; Based on the target voucher data in the sample data directory, a voucher data model is constructed with the voucher as a dimension, including: Extract target voucher data from the sample data directory, and segment the voucher summary in the target voucher data; Based on the word segmentation results, extract voucher data from the target voucher data using units, cities and provinces as dimensions; Build a voucher data model based on dimensions, word segmentation results and extracted voucher data.

2. The credential generation method according to claim 1, characterized in that: Filtering target voucher data from a historical voucher data set and outputting the target voucher data to a sample data directory includes: Extracting historical voucher data from a historical voucher data set, and generating a feature vector of the historical voucher data based on a preset data indicator; Calculating the similarity between the feature vector of the historical voucher data and the feature vector of the comparison voucher data; When the similarity is greater than a set threshold, the historical credential data is output as target credential data to the sample data directory.

3. The credential generation method according to claim 1, characterized in that: Insert the target voucher data in the data queue into the unit transition model according to the pre-set element insertion order, including: Extracting target voucher data from the data queue in sequence, obtaining target indicator data in the target voucher data, and inserting the target indicator data into the unit transition model when the target indicator data is not included in the existing indicator data of the unit transition model; the target indicator data includes an entry summary, a subject, and an amount; Extracting the target time in the target voucher data, inserting the target time into the unit transition model if the target time is not included in the existing time in the unit transition model, and associating the target time with the target indicator data; The target unit in the target voucher data is obtained, and when the target unit is not included in the existing units in the unit transition model, the target unit is inserted into the unit transition model, and the target unit is associated with the target time.

4. The credential generation method according to claim 1 or 3, characterized in that: In response to a user initiating a credential generation instruction, generating a target credential matching a generation element in the credential generation instruction based on the data model, including: In response to a user initiating a credential generation instruction, obtaining a credential generation cycle in the credential generation instruction; Acquire system time, extract voucher data in the unit data model according to the system time and the voucher generation period, and generate a periodic voucher data list; According to the target period selected by the user, extracting the target period data corresponding to the target period from the periodic voucher list, and generating the target voucher according to the target period data; According to the voucher data extraction range, the voucher data is extracted from the unit data model, and the target voucher is generated according to the extracted voucher data.

5. The credential generation method according to claim 1, characterized in that: In response to a user initiating a credential generation instruction, generating a target credential matching a generation element in the credential generation instruction based on the data model, further comprising: In response to a user initiating a credential generation instruction, obtaining a credential keyword in the credential generation instruction; Perform keyword matching in the voucher data model to obtain first voucher data matching the voucher keyword, and fill the first voucher data into the initial voucher to obtain a transition voucher; According to the voucher keyword and the subject to which the target voucher data belongs, second voucher data is obtained in the entry data model, and the transition voucher is completed using the second voucher data to obtain the target voucher.

6. The method for generating a voucher according to claim 5, characterized in that: In response to a user initiating a credential generation instruction, generating a target credential matching a generation element in the credential generation instruction based on the data model, further comprising: If the voucher keyword is not matched in the voucher data model, extracting the entry summary, subject and amount of each entry in the entry data model in sequence, and generating an entry feature vector based on the entry summary, subject and amount; The feature vector of the voucher keyword is compared with the entry feature vector. When the similarity is higher than a set threshold, a target voucher is constructed based on the target voucher data associated with the entry feature vector.

7. A credential generating device, characterized in that: include: A voucher data screening module, used to screen target voucher data in a historical voucher data set and output the target voucher data to a sample data directory; A data model building module, used to build a data model based on the target voucher data in the sample data directory, with units, entries and vouchers as dimensions; A credential generation module, configured to generate, in response to a credential generation instruction initiated by a user, a target credential matching a generation element in the credential generation instruction based on the data model; The data model building module includes: A code acquisition unit, used to traverse the target credential data in the sample data directory and acquire a unit cyclic redundancy check CRC code corresponding to the target credential data; A data grouping unit, used for grouping the target voucher data based on the unit CRC encoding, and transferring the target voucher data into the corresponding data queue according to the grouping; The data insertion unit is used to start the model building task corresponding to each data queue in parallel, and insert the target voucher data in the data queue into the unit transition model according to the pre-set element insertion order; A unit data model construction unit, configured to determine the unit transition model as a unit data model after inserting target voucher data in all data queues into the unit transition model; The data model building module further includes: A target entry acquisition unit is used to extract target voucher data from the sample data directory, and sequentially acquire the entries to be entered in the target voucher data as target entries; An entry comparison unit is used to compare the target entry with the existing entries in the entry transition model, and if there is no existing entry with a similarity with the target entry higher than a set threshold, insert the target voucher data into the entry transition model; a voucher determination unit, configured to determine, in the entry transition model, a first voucher to which the first existing entry belongs if there is a first existing entry whose similarity to the target entry is higher than a set threshold; a voucher merging unit, configured to compare each existing entry in the first voucher with each entry to be entered in the target voucher data, and merge the target voucher data with the first voucher when the entries to be entered with a similarity greater than a set threshold account for a set proportion of all the entries to be entered in the target voucher data; The entry data model building unit is used to use the entry transition model obtained after traversing the target voucher data in the sample data directory as the entry data model; The data model building module further includes: A summary word segmentation unit is used to extract target voucher data from the sample data directory and perform word segmentation on the voucher summary in the target voucher data; A voucher data extraction unit is used to extract voucher data from target voucher data based on word segmentation results and taking units, cities and provinces as dimensions; The voucher data model building unit is used to build a voucher data model based on dimensions, word segmentation results and extracted voucher data.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the credential generation method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the credential generation method according to any one of claims 1 to 6 when executed.

Images